Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection

Abstract

Over the past decade, deep neural networks (DNNs) have demonstrated remarkable performance in a variety of applications. As we try to solve more advanced problems, increasing demands for computing and power resources has become inevitable. Spiking neural networks (SNNs) have attracted widespread interest as the third-generation of neural networks due to their event-driven and low-powered nature. SNNs, however, are difficult to train, mainly owing to their complex dynamics of neurons and non-differentiable spike operations. Furthermore, their applications have been limited to relatively simple tasks such as image classification. In this study, we investigate the performance degradation of SNNs in a more challenging regression problem (i.e., object detection). Through our in-depth analysis, we introduce two novel methods: channel-wise normalization and signed neuron with imbalanced threshold, both of which provide fast and accurate information transmission for deep SNNs. Consequently, we present a first spiked-based object detection model, called Spiking-YOLO. Our experiments show that Spiking-YOLO achieves remarkable results that are comparable (up to 98%) to those of Tiny YOLO on non-trivial datasets, PASCAL VOC and MS COCO. Furthermore, Spiking-YOLO on a neuromorphic chip consumes approximately 280 times less energy than Tiny YOLO and converges 2.3 to 4 times faster than previous SNN conversion methods.

Accepted to AAAI 2020

References in corpus (12)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Distilling the Knowledge in a Neural Network
• YOLOv3: An Incremental Improvement
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Compressing Deep Convolutional Networks using Vector Quantization
• Binarized Neural Networks
• Channel Pruning for Accelerating Very Deep Neural Networks
• Deep Learning for Generic Object Detection: A Survey
• Dynamic Network Surgery for Efficient DNNs
• Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networks
• Direct Training for Spiking Neural Networks: Faster, Larger, Better
• Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks

Cited by in corpus (4)

• LittleYOLO-SPP: A Delicate Real-Time Vehicle Detection Algorithm
• Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks
• A Temporal Neural Network Architecture for Online Learning
• Spiking CapsNet: A Spiking Neural Network With A Biologically Plausible Routing Rule Between Capsules